A guide for maintaining CHANGELOG.md, the file that records user-visible changes between software releases, using the Keep a Changelog format and semantic versioning.

Use it when creating or reviewing an Unreleased section, checking commits for missing entries, or preparing changelog content for a release.

It helps distinguish changes users need to know about from internal work and avoids editing changelogs that are generated automatically.

changelog — Skill for Claude Code and Codex by alunduil

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add alunduil/alunduil-chezmoi --skill changelog

Clone the repo

git clone --depth 1 https://github.com/alunduil/alunduil-chezmoi

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/changelog/github.svg)](https://agentmods.dev/skills/alunduil/alunduil-chezmoi/changelog)

Your own site

<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/changelog"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/changelog/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/changelog"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/changelog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,543 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00089	$0.01543
Opus 5	$0.00044	$0.00772
Sonnet 5	$0.00018	$0.00309
Haiku 4.5	$0.00009	$0.00154

Measured 12d ago against content hash 3b262eceb830, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

changelog scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

dot_claude/skills/changelog/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Changelog

References: https://keepachangelog.com/en/1.1.0/, https://semver.org/, https://pvp.haskell.org/.

This skill maintains a hand-curated KAC. It detects auto-managed setups and steps aside; it never proposes adopting tooling. Cutting a release (tagging, version-file edits) is out of scope — bootstrap and review-against-commits only.

Defer to auto-tooling

If any are present the changelog is auto-managed — surface the detection and stop unless the user overrides:

.changeset/ — changesets
.release-please-manifest.json / release-please-config.json — release-please
cliff.toml / .cliff.toml — git-cliff
package.json "release" / "semantic-release", or .releaserc* / release.config.* — semantic-release
pyproject.toml [tool.towncrier], or newsfragments/ — towncrier

Treat any clearly auto-managed CHANGELOG the same way.

What to include

Entries describe changes visible to consumers of the deliverable — users of the library / CLI / service, not contributors to the repo.

Include: public API changes (additions, removals, renames, signatures), observable behavior changes (output, errors, defaults), user-facing bug fixes, perceptible performance changes, security fixes, breaking deprecations, and supported-platform / runtime / dependency changes users must adapt to.

Skip: typos, comment-only changes, internal refactors, test changes, build/CI tweaks, dependency bumps users don't perceive, doc fixes (unless docs are the deliverable), and fixes for bugs no released version exhibited.

The test: "would a user of this project notice or care?" If no, skip.

Ruling-out heuristic: if removing the entry would leave the eventual release notes equally accurate, it doesn't belong. This catches both the user-impact failures above and pre-release deltas-of-deltas (see Pre-first-release mode).

Pre-first-release mode

Detect: git tag is empty AND no version sections appear below [Unreleased]. The project has never shipped — surface this explicitly and switch behavior.

Read the full file on GitHub · 86 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 86 lines · 89 tokens per session scan A 3b262eceb830

Subscribe to this mod's changes

changelog is a skill published in the GitHub repository alunduil/alunduil-chezmoi (2 stars, last pushed today), licensed 0BSD. It adds 89 tokens to every session and 1,543 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Git and workflow Releases Writing and docs chezmoi crostini debian dotfiles

sync-release

Owns release-pipeline conventions: sr.yaml schema, the sr CLI verbs (init/plan/prepare/ release) and urmzd/sr action, typed publishers (cargo/npm/pypi/docker/go/custom), monorepo workspace discovery, versionfiles/stagefiles mapping, and post-release patterns. Language-specific build targets live in scaffold-rust…

urmzd/dotfiles · 136 tokens

setup-ci

Defines GitHub Actions workflow structure: ci.yml + release.yml naming, concurrency groups, bot-commit skip, workflowcall reuse, App-token checkout, and optional fsrc/teasr steps. Language-specific pipelines live in scaffold-rust, scaffold-go, scaffold-python, scaffold-node, scaffold-terraform. Use when setting up…

urmzd/dotfiles · 119 tokens

release-audit

Audit GitHub releases, git tags, and release assets for one repo or every repo in a directory. Flags orphaned tags, missing binaries/checksums, draft releases, floating tag drift, pre-release remnants, and (when sr.yaml is present) sr config issues. Read-only: never deletes or modifies tags/releases. Use when checking…

urmzd/dotfiles · 126 tokens

changelog